Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FRECPE (scalar, H)

Test 1: uops

Code:

  frecpe h0, h0
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)0308091e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a7a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220000611900251000100010001044513018303730372738328951000100010003037303711100110000073216112919100030383038303830383038
10043037230000611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037230090611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037230030611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372200001031900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037220000611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037230000841900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037230000611900251000100010001044513018303730372738328951000100010003037303711100110000173116112919100030383038303830383038
100430372310120611900251000100010001044513018303730372738328951000100010003037303711100110002073116112919100030383038303830383038
10043037230000611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpe h0, h0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a1e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722511061199002510100100100001001000050010674511300183003730037285956287401010020010008200100083003730037111020110099100100100001000011171711611299330100001003003830038300383003830038
102043003722511361199002510100100100001001000050010674511300183003730037285956287411010020010008200100083003730037111020110099100100100001003011171711611299340100001003003830038300383003830038
1020430037224113061199002510100100100001001000050010674511300183003730037285956287411010020010008200100083003730037111020110099100100100001000011171711611299340100001003003830038300383003830038
10204300372251114761199002510100100100001001000050010674511300543003730037285957287411010020010008200100083003730037111020110099100100100001000011171811611299340100001003003830038300383003830038
1020430037224111861199002510100100100001001000050010674511300183003730037285956287401010020010008200100083003730037111020110099100100100001000000071021622299190100001003003830038300383003830038
102043003722500061199002510100100100001001000050010674511300183003730037285883287451010020010000200100003003730037111020110099100100100001000000071021622299190100001003003830038300383003830038
1020430037226001561199002510100100100001001000050010674511300183003730037285883287451010020010000200100003003730037111020110099100100100001000000071021622299190100001003003830038300383003830038
1020430037224003661199002510100100100001001000050010674511300183003730037285883287451010020010000200100003003730037111020110099100100100001000000071021622299190100001003003830038300383003830038
102043003722500061199002510100100100001001000050010674511300183003730037285883287451010020010000200100003003730037111020110099100100100001000000071021622299190100001003003830038300383003830038
102043003722400061199002510100100100001001000050010674511300183003730037285883287451010020010000200100003003730037111020110099100100100001000000071021622299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251206119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640316222991910000103003830038300383003830038
10024300372251506119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372251206119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001010640216222991910000103003830038300383003830038
10024300372252406119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372251206119900251001010100001010000501067451300183003730037286103287671001020100002010000300853003721100211091010100001000640216222991910000103003830038300383003830038
1002430037225006119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722518072619900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
1002430037225906119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372251506119900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722512053619900251001010100001010000501067451300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frecpe h0, h8
  frecpe h1, h8
  frecpe h2, h8
  frecpe h3, h8
  frecpe h4, h8
  frecpe h5, h8
  frecpe h6, h8
  frecpe h7, h8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030b181e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204800396000003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800396000003925801001008000010080000500640000080020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800395990003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800395990003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800395990003925801001008000010080000500640000080020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800396000003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008008980040800408004080040
80204800395990003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800395990003925801001008000010080000500640000080020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800396000003925801001008000010080000500640000180020080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800396000003925801001008000010080000500640418180020080039800396997166999380100200800082008005580039800391180201100991001008000010001790611151170160080150800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030708090a0b191e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a7a8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800248004060000000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010000000502051665800340080000108004080040800408004080040
800248003959900000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010001000502081675800340080000108004080040800408004080040
800248003959900000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010000000502071665800340080000108004080040800408004080040
800248003959900010005025800101080000108000050640000008002080039800396998637001980010208000020800008003980039118002110910108000010000000502081667800340080000108004080040800408004080040
800248003959900000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010000000502061697800340080000108004080040800408004080040
800248003960000000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010000000502061667800340080000108004080040800408004080040
800248003959900000005025800101080000108000050640000008002080039800396998637001980010208000020800008003980039118002110910108000010000000502051656800340080000108004080040800408004080040
800248003960000000005025800101080000108000050640000008002080039800396998637001980010208000020800008003980039118002110910108000010000000502081665800340080000108004080040800408004080040
8002480039599000000050258001010800001080000506400001180020800398003969986370057800102080000208000080039800391180021109101080000100000005020816568003401680000108004080040800408004080040
800248003959900000005025800101080000108000050640000018002080039800396998637001980010208000020800008003980039118002110910108000010000000502051666800340080000108004080040800408004080040